主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2026, Vol. 34 ›› Issue (7): 157-165.doi: 10.16381/j.cnki.issn1003-207x.2023.1666

• • 上一篇    

考虑模态可信度的产品评论有用性识别研究

杨颖1,2,3, 唐思1,2, 王安宁1,3(), 张强1,3   

  1. 1.合肥工业大学管理学院 安徽 合肥 230009
    2.过程优化与智能决策教育部重点实验室 安徽 合肥 230009
    3.智能决策与信息系统技术教育部工程研究中心,安徽 合肥 230009
  • 收稿日期:2023-10-12 修回日期:2025-01-12 出版日期:2026-07-25 发布日期:2026-06-18
  • 通讯作者: 王安宁 E-mail:waning@hfut.edu.cn
  • 基金资助:
    国家自然科学基金项目(72071061);国家自然科学基金项目(72101078);国家自然科学基金项目(72171069);中央高校基本科研业务费专项资金项目(JZ2023YQTD0075);中央高校基本科研业务费专项资金项目(Z2023HGTB0280)

Identification of Usefulness for Online Review Considering the Reliability of Modalities

Ying Yang1,2,3, Si Tang1,2, Anning Wang1,3(), Qiang Zhang1,3   

  1. 1.School of Management,Hefei University of Technology,Hefei 230009,China
    2.Key Laboratory of Process Optimization & Intelligent Decision-making,Ministry of Education,Hefei University of Technology,Hefei 230009,China
    3.Engineering Research Center for Intelligent Decision-Making & Information System Technologies,Ministry of Education,Hefei 230009,China
  • Received:2023-10-12 Revised:2025-01-12 Online:2026-07-25 Published:2026-06-18
  • Contact: Anning Wang E-mail:waning@hfut.edu.cn

摘要:

包含文本和图片的多模态产品评论已经成为电商平台上客户表达意见和形成口碑的主流形式。考虑到这两种分布异质的多模态数据的自身可靠性及其对产品在线评论价值影响的差异性,本文提出了一种考虑多模态可信度的在线产品评论有用性识别方法。利用该方法,充分考虑了文本和图片模态数据的异质性,并通过不同模态数据的交互获得模态间的一致性;设计了一个可信多视图融合模块,对单模态和跨模态视图进行不确定性估计,通过动态的证据融合策略和对比学习策略提高模型的整体可信度。在亚马逊网站的智能手机和家居用品等产品评论数据集上进行实例验证,结果表明,所提方法能够有效提升在线产品评论有用性识别的准确性,同时,增加了模型决策结果的可解释性。

关键词: 在线产品评论, 有用性识别, 多模态融合, 可信多视图学习

Abstract:

Multimodal product reviews, which include both text and images, have become the mainstream way for customers to express opinions and share word-of-mouth on e-commerce platforms. Previous studies on multimodal review usefulness primarily focus on feature representation and fusion, often neglecting the reliability of multimodal data. Considering the heterogeneity of these two types of multimodal data and their varying degrees of reliability in influencing the value of online product reviews, an online product review helpfulness recognition method is propased that incorporates multimodal credibility. The method fully accounts for the heterogeneity of textual and visual modalities and captures consistency information between modalities through their interaction. A credible multi-view fusion module is designed to estimate the uncertainty of both unimodal and cross-modal views, improving the overall reliability of the model through a dynamic evidence fusion strategy and a contrastive learning strategy. Empirical validation on multiple product review datasets from Amazon demonstrates that the proposed method effectively enhances the accuracy of online product review helpfulness recognition while increasing the interpretability of the model’s decision-making results.

Key words: online product reviews, helpfulness prediction, multimodal fusion, trusted multi-view learning

中图分类号: